cataphract                               Sun, 24 Oct 2010 19:05:21 +0000

Revision: http://svn.php.net/viewvc?view=revision&revision=304708

Log:
- Removed out-of-date comments and one enum constant from html_tables.h and its 
generator.
- Other minor aesthetic improvements in the generator.

Changed paths:
    U   php/php-src/trunk/ext/standard/html_tables/html_table_gen.php
    U   php/php-src/trunk/ext/standard/html_tables.h

Modified: php/php-src/trunk/ext/standard/html_tables/html_table_gen.php
===================================================================
--- php/php-src/trunk/ext/standard/html_tables/html_table_gen.php	2010-10-24 16:57:27 UTC (rev 304707)
+++ php/php-src/trunk/ext/standard/html_tables/html_table_gen.php	2010-10-24 19:05:21 UTC (rev 304708)
@@ -51,17 +51,9 @@
 ***************************************************************************
 **************************************************************************/

-/* cs_terminator is overloaded in the following fashion:
- * - It terminates the list entity maps.
- * - In BG(inverse_ent_maps), it's the key of the inverse map that stores
- *   only the basic entities.
- * - When passed to traverse_for_entities (or via php_unescape_entities with !all),
- *   we don't care about the encoding (UTF-8 is chosen, but it should be used
- *   when it doesn't matter).
- */
-enum entity_charset { cs_terminator, cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15,
-					  cs_cp1251, cs_8859_5, cs_cp866, cs_macroman, cs_koi8r,
-					  cs_big5, cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
+enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
+					  cs_8859_5, cs_cp866, cs_macroman, cs_koi8r, cs_big5,
+					  cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
 					  cs_numelems /* used to count the number of charsets */
 					};
 #define CHARSET_UNICODE_COMPAT(cs)	((cs) <= cs_utf_8)
@@ -72,36 +64,36 @@
 	const char *codeset;
 	enum entity_charset charset;
 } charset_map[] = {
-	{ "ISO-8859-1", 	cs_8859_1 },
-	{ "ISO8859-1",	 	cs_8859_1 },
-	{ "ISO-8859-15", 	cs_8859_15 },
-	{ "ISO8859-15", 	cs_8859_15 },
-	{ "utf-8", 			cs_utf_8 },
+	{ "ISO-8859-1",		cs_8859_1 },
+	{ "ISO8859-1",		cs_8859_1 },
+	{ "ISO-8859-15",	cs_8859_15 },
+	{ "ISO8859-15",		cs_8859_15 },
+	{ "utf-8",			cs_utf_8 },
 	{ "cp1252", 		cs_cp1252 },
-	{ "Windows-1252", 	cs_cp1252 },
-	{ "1252",           cs_cp1252 },
+	{ "Windows-1252",	cs_cp1252 },
+	{ "1252",			cs_cp1252 },
 	{ "BIG5",			cs_big5 },
-	{ "950",            cs_big5 },
+	{ "950",			cs_big5 },
 	{ "GB2312",			cs_gb2312 },
-	{ "936",            cs_gb2312 },
+	{ "936",			cs_gb2312 },
 	{ "BIG5-HKSCS",		cs_big5hkscs },
 	{ "Shift_JIS",		cs_sjis },
-	{ "SJIS",   		cs_sjis },
-	{ "932",            cs_sjis },
-	{ "EUCJP",   		cs_eucjp },
-	{ "EUC-JP",   		cs_eucjp },
-	{ "KOI8-R",         cs_koi8r },
-	{ "koi8-ru",        cs_koi8r },
-	{ "koi8r",          cs_koi8r },
-	{ "cp1251",         cs_cp1251 },
-	{ "Windows-1251",   cs_cp1251 },
-	{ "win-1251",       cs_cp1251 },
-	{ "iso8859-5",      cs_8859_5 },
-	{ "iso-8859-5",     cs_8859_5 },
-	{ "cp866",          cs_cp866 },
-	{ "866",            cs_cp866 },
-	{ "ibm866",         cs_cp866 },
-	{ "MacRoman",       cs_macroman },
+	{ "SJIS",			cs_sjis },
+	{ "932",			cs_sjis },
+	{ "EUCJP",			cs_eucjp },
+	{ "EUC-JP",			cs_eucjp },
+	{ "KOI8-R",			cs_koi8r },
+	{ "koi8-ru",		cs_koi8r },
+	{ "koi8r",			cs_koi8r },
+	{ "cp1251",			cs_cp1251 },
+	{ "Windows-1251",	cs_cp1251 },
+	{ "win-1251",		cs_cp1251 },
+	{ "iso8859-5",		cs_8859_5 },
+	{ "iso-8859-5",		cs_8859_5 },
+	{ "cp866",			cs_cp866 },
+	{ "866",			cs_cp866 },
+	{ "ibm866",			cs_cp866 },
+	{ "MacRoman",		cs_macroman },
 	{ NULL }
 };

@@ -132,51 +124,51 @@
 $encodings = array(
     array(
         "ident" => "iso88591",
-        "enumid" => 2,
+        "enumid" => 1,
         "name" => "ISO-8859-1",
         "file" => "mappings/8859-1.TXT",
     ),
     array(
         "ident" => "iso88595",
-        "enumid" => 6,
+        "enumid" => 5,
         "name" => "ISO-8859-5",
         "file" => "mappings/8859-5.TXT",
     ),
     array(
         "ident" => "iso885915",
-        "enumid" => 4,
+        "enumid" => 3,
         "name" => "ISO-8859-15",
         "file" => "mappings/8859-15.TXT",
     ),
     array(
         "ident" => "win1252",
-        "enumid" => 3,
+        "enumid" => 2,
         "enumident" => "cp1252",
         "name" => "Windows-1252",
         "file" => "mappings/CP1252.TXT",
     ),
     array(
         "ident" => "win1251",
-        "enumid" => 5,
+        "enumid" => 4,
         "enumident" => "cp1252",
         "name" => "Windows-1251",
         "file" => "mappings/CP1251.TXT",
     ),
     array(
         "ident" => "koi8r",
-        "enumid" => 9,
+        "enumid" => 8,
         "name" => "KOI8-R",
         "file" => "mappings/KOI8-R.TXT",
     ),
     array(
         "ident" => "cp866",
-        "enumid" => 7,
+        "enumid" => 6,
         "name" => "CP-866",
         "file" => "mappings/CP866.TXT",
     ),
     array(
         "ident" => "macroman",
-        "enumid" => 8,
+        "enumid" => 7,
         "name" => "MacRoman",
         "file" => "mappings/ROMAN.TXT",
     ),
@@ -336,7 +328,7 @@
     $lines = explode("\n", file_get_contents($e{'file'}));
     foreach ($lines as $l) {
         if (preg_match("/^0x([0-9A-Z]{2})\t0x([0-9A-Z]{2,})\s+#\s*(.*)$/i", $l, $matches))
-            $map[] = array($matches[1], $matches[2], $matches[3]);
+            $map[] = array($matches[1], $matches[2], rtrim($matches[3]));
     }

     $mappy = array();
@@ -420,7 +412,7 @@
 	const entity_stage3_row *table;
 } entity_table_opt;

-/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistentcy's sake. */
+/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistency's sake. */


 CODE;

Modified: php/php-src/trunk/ext/standard/html_tables.h
===================================================================
--- php/php-src/trunk/ext/standard/html_tables.h	2010-10-24 16:57:27 UTC (rev 304707)
+++ php/php-src/trunk/ext/standard/html_tables.h	2010-10-24 19:05:21 UTC (rev 304708)
@@ -1,4 +1,4 @@
-/*
+/*
    +----------------------------------------------------------------------+
    | PHP Version 5                                                        |
    +----------------------------------------------------------------------+
@@ -28,17 +28,9 @@
 ***************************************************************************
 **************************************************************************/

-/* cs_terminator is overloaded in the following fashion:
- * - It terminates the list entity maps.
- * - In BG(inverse_ent_maps), it's the key of the inverse map that stores
- *   only the basic entities.
- * - When passed to traverse_for_entities (or via php_unescape_entities with !all),
- *   we don't care about the encoding (UTF-8 is chosen, but it should be used
- *   when it doesn't matter).
- */
-enum entity_charset { cs_terminator, cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15,
-					  cs_cp1251, cs_8859_5, cs_cp866, cs_macroman, cs_koi8r,
-					  cs_big5, cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
+enum entity_charset { cs_utf_8, cs_8859_1, cs_cp1252, cs_8859_15, cs_cp1251,
+					  cs_8859_5, cs_cp866, cs_macroman, cs_koi8r, cs_big5,
+					  cs_gb2312, cs_big5hkscs, cs_sjis, cs_eucjp,
 					  cs_numelems /* used to count the number of charsets */
 					};
 #define CHARSET_UNICODE_COMPAT(cs)	((cs) <= cs_utf_8)
@@ -49,36 +41,36 @@
 	const char *codeset;
 	enum entity_charset charset;
 } charset_map[] = {
-	{ "ISO-8859-1", 	cs_8859_1 },
-	{ "ISO8859-1",	 	cs_8859_1 },
-	{ "ISO-8859-15", 	cs_8859_15 },
-	{ "ISO8859-15", 	cs_8859_15 },
-	{ "utf-8", 			cs_utf_8 },
+	{ "ISO-8859-1",		cs_8859_1 },
+	{ "ISO8859-1",		cs_8859_1 },
+	{ "ISO-8859-15",	cs_8859_15 },
+	{ "ISO8859-15",		cs_8859_15 },
+	{ "utf-8",			cs_utf_8 },
 	{ "cp1252", 		cs_cp1252 },
-	{ "Windows-1252", 	cs_cp1252 },
-	{ "1252",           cs_cp1252 },
+	{ "Windows-1252",	cs_cp1252 },
+	{ "1252",			cs_cp1252 },
 	{ "BIG5",			cs_big5 },
-	{ "950",            cs_big5 },
+	{ "950",			cs_big5 },
 	{ "GB2312",			cs_gb2312 },
-	{ "936",            cs_gb2312 },
+	{ "936",			cs_gb2312 },
 	{ "BIG5-HKSCS",		cs_big5hkscs },
 	{ "Shift_JIS",		cs_sjis },
-	{ "SJIS",   		cs_sjis },
-	{ "932",            cs_sjis },
-	{ "EUCJP",   		cs_eucjp },
-	{ "EUC-JP",   		cs_eucjp },
-	{ "KOI8-R",         cs_koi8r },
-	{ "koi8-ru",        cs_koi8r },
-	{ "koi8r",          cs_koi8r },
-	{ "cp1251",         cs_cp1251 },
-	{ "Windows-1251",   cs_cp1251 },
-	{ "win-1251",       cs_cp1251 },
-	{ "iso8859-5",      cs_8859_5 },
-	{ "iso-8859-5",     cs_8859_5 },
-	{ "cp866",          cs_cp866 },
-	{ "866",            cs_cp866 },
-	{ "ibm866",         cs_cp866 },
-	{ "MacRoman",       cs_macroman },
+	{ "SJIS",			cs_sjis },
+	{ "932",			cs_sjis },
+	{ "EUCJP",			cs_eucjp },
+	{ "EUC-JP",			cs_eucjp },
+	{ "KOI8-R",			cs_koi8r },
+	{ "koi8-ru",		cs_koi8r },
+	{ "koi8r",			cs_koi8r },
+	{ "cp1251",			cs_cp1251 },
+	{ "Windows-1251",	cs_cp1251 },
+	{ "win-1251",		cs_cp1251 },
+	{ "iso8859-5",		cs_8859_5 },
+	{ "iso-8859-5",		cs_8859_5 },
+	{ "cp866",			cs_cp866 },
+	{ "866",			cs_cp866 },
+	{ "ibm866",			cs_cp866 },
+	{ "MacRoman",		cs_macroman },
 	{ NULL }
 };

@@ -476,7 +468,6 @@
 /* {{{ Index of tables for encoding conversion */
 static const enc_to_uni *const enc_to_uni_index[cs_numelems] = {
 	NULL,
-	NULL,
 	&enc_to_uni_iso88591,
 	&enc_to_uni_win1252,
 	&enc_to_uni_iso885915,
@@ -1144,7 +1135,7 @@
 	const entity_stage3_row *table;
 } entity_table_opt;

-/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistentcy's sake. */
+/* Replaced "GT" > "gt" and "QUOT" > "quot" for consistency's sake. */

 /* {{{ Start of HTML5 multi-stage table for codepoint -> entity */

-- 
PHP CVS Mailing List (http://www.php.net/)
To unsubscribe, visit: http://www.php.net/unsub.php

Reply via email to